https://hackerpaper.kaipfister.de/p/2205.06977/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=43516658urn:hackerpapers:mention:2205.06977:43516658Sat, 29 Mar 2025 16:27:47 GMT<p>As an intuition on why many people see this as different. PAC Learning is about compression, KF/EKF is more like Taylor expansion. The specific types of PAC Learning that this paper covers has problems with a simplicity bias, and fairly low sensitivity. While based on UHATs, this paper may provide some insights. https://arxiv.org/abs/2502.02393 Obviously LLM and LRMs are the most studied, but even the recent posts on here from anthropic show that without a few high probability entries in the k-top results, confabulations are difficult for transformers. Obviously there are PAC Learning methods…</p><p><a href="https://hackerpaper.kaipfister.de/p/2205.06977/">Paper and discussion history</a>. A mention is not an endorsement.</p>quant-ph